Soft sensor for and using dynamic neural networks

Shakil, M.; Elshafei, Moustafa; Habib, Mohamed A.; Maleki, F. A.

doi:10.1016/j.compeleceng.2008.08.007

Cited by 79 publications

(38 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Soft computing techniques, such as statistical methods and heuristics, have been gaining momentum recently as viable alternatives to hardware sensors. For example, artificial neural networks, fuzzy logic, genetic algorithms and support vector machines have all been used to predict pollutant emissions from fossil fuel fired combustion processes [4][5][6][7][8][9]. Ikonen et al [4] described a distributed logic processor based on neurofuzzy methods to predict flue gas emissions in a power plant, where the flue-gas oxygen, estimates of residence time, and primary air stoichiometry were used as input signals to the model.…”

Section: Introductionmentioning

confidence: 99%

Prediction of NOx emissions throughflame radical imaging and neural network based soft computing

Sun

Lü

et al. 2012

2012 IEEE International Conference on Imaging Systems and Techniques Proceedings

View full text Add to dashboard Cite

The characteristics of reacting radicals in a flame are crucial for an in-depth understanding of the formation process of combustion emissions. This paper presents an algorithm for the prediction of NOx (NO and NO 2 ) emissions in flue gas through flame radical imaging, flame temperature monitoring and application of Neural Network techniques. Radiation images of flame radicals OH*, CN*, CH* and C 2 * are captured using an intensified multi-wavelength imaging system. Flame temperature is determined using a spectrometer and two-color pyrometry. Based on these images, the characteristic values of the flame radicals are extracted. These characteristic values, together with the flame temperature, are then used to predict NOx emissions. Experimental results from a laboratory-scale gas-fired combustion rig have shown the effectiveness of the proposed method for the prediction of NOx emissions.

show abstract

Section: Introductionmentioning

confidence: 99%

Prediction of NOx emissions throughflame radical imaging and neural network based soft computing

Sun

Lü

et al. 2012

2012 IEEE International Conference on Imaging Systems and Techniques Proceedings

View full text Add to dashboard Cite

show abstract

“…measurement data) are a potential approach to be used as the basis of advanced monitoring systems. For example, model-predictive monitoring of emissions has been of wider interest recently, and methods such as neural networks are widely used as the basis of predictive emission monitoring systems (Iliyas, Elshafei, Habib, & Adeniran, 2013;Lv, Liu, Yang, & Zeng, 2013;Shakil, Elshafei, Habib, & Maleki, 2009;Smrekar, Potočnik, & Senegačnik, 2013). A descriptive data-based system for monitoring and evaluating dynamic industrial processes has to be able to process a large amount of multivariate data, extract the fundamental information from the data, and provide an understandable presentation of this information to be evaluated by experts.…”

Section: Introductionmentioning

confidence: 99%

Monitoring and analysis of air emissions based on condition models derived from process history

Liukkonen

Hiltunen²

2016

Cogent Engineering

View full text Add to dashboard Cite

Evaluation of online information on operating conditions is necessary when reducing air emissions in energy plants. In this respect, automated monitoring and control are of primary concern, particularly in biomass combustion. As monitoring of emissions in power plants is ever more challenging because of lowgrade fuels and fuel mixtures, new monitoring applications are needed to extract essential information from the large amount of measurement data. The management of emissions in energy boilers lacks economically efficient, fast, and competent computational systems that could support decision-making regarding the improvement of emission efficiency. In this paper, a novel emission monitoring platform based on the self-organizing map method is presented. The system is capable, not only of visualizing the prevailing status of the process and detecting problem situations (i.e. increased emission release rates), but also of analyzing these situations automatically and presenting factors potentially affecting them. The system is demonstrated using measurement data from an industrial circulating fluidized bed boiler fired by forest residue as the primary fuel and coal as the supporting fuel.

show abstract

“…The Mallows Coefficient method with non-linear models is computationally expensive when the input dimensionality high. A linear time-lag model optimized by a genetic algorithm was proposed by [11] to perform delay selection, and it had a good performance to predicting the nitrogen oxides N O X and oxygen O 2 in the combustion operation in industrial boilers. In [2] the proposed method first selects the best input variables by means of self-organizing map (SOM) and then selects the best time-lags using the Lipschitz quotients.…”

Section: Introductionmentioning

confidence: 99%

“…In the first approach, it is assumed that the best variables are known, remaining the selection of the best time-lag for each variable [3,11]; generally the variables are selected by an expert, this is a good way for selection, but for generic applications or complex processes this analysis can be very complicated, expensive and/or inaccurate. In the second approach, it is assumed that both the best variables and respective timelag are unknown [2,9,12].…”

Section: Introductionmentioning

confidence: 99%

Variable and time-lag selection using empirical data

Souza

Araújo

2011

Etfa2011

View full text Add to dashboard Cite

The paper proposes a method to select the best variables and respective time-lags for industrial applications when the objective is the estimation of a target variable using the information content of empirical data. No further information is assumed about the process. The problem of jointly selecting the best variables and the respective time-lags is treated as a variable selection problem. This assumption implies an increase of input dimensionality and multicollinearity into input space. Then, a multidimensional mutual information estimator based on the l-nearest neighbor algorithm is used in a forward search procedure to select the best variables and and respective time-lags. To verify the performance of selected variables and delays, the method was successfully applied in two data sets. A least squares support vector machine was used as the main model for the soft sensor in both cases.

show abstract

Soft sensor for and using dynamic neural networks

Cited by 79 publications

References 8 publications

Prediction of NOx emissions throughflame radical imaging and neural network based soft computing

Prediction of NOx emissions throughflame radical imaging and neural network based soft computing

Monitoring and analysis of air emissions based on condition models derived from process history

Variable and time-lag selection using empirical data

Contact Info

Product

Resources

About